com1
Browse files- config.json +33 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.txt +5 -0
- trainer_state.json +529 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "kykim/bert-kor-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"directionality": "bidi",
|
| 9 |
+
"embedding_size": 768,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-12,
|
| 17 |
+
"max_position_embeddings": 512,
|
| 18 |
+
"model_type": "bert",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_layers": 12,
|
| 21 |
+
"pad_token_id": 0,
|
| 22 |
+
"pooler_fc_size": 768,
|
| 23 |
+
"pooler_num_attention_heads": 12,
|
| 24 |
+
"pooler_num_fc_layers": 3,
|
| 25 |
+
"pooler_size_per_head": 128,
|
| 26 |
+
"pooler_type": "first_token_transform",
|
| 27 |
+
"position_embedding_type": "absolute",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.12.2",
|
| 30 |
+
"type_vocab_size": 2,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 42000
|
| 33 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52150ce0036b7b636133cb5745af380a92be2ad104e44e798b3902a0253dffcf
|
| 3 |
+
size 602629988
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "kykim/bert-kor-base", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
|
train_results.txt
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch = 6.0
|
| 2 |
+
train_loss = 1.717211879325718
|
| 3 |
+
train_runtime = 1445.1612
|
| 4 |
+
train_samples_per_second = 93.037
|
| 5 |
+
train_steps_per_second = 2.91
|
trainer_state.json
ADDED
|
@@ -0,0 +1,529 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
+
"global_step": 4206,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.07,
|
| 12 |
+
"learning_rate": 4.940561103185925e-05,
|
| 13 |
+
"loss": 2.1393,
|
| 14 |
+
"step": 50
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.14,
|
| 18 |
+
"learning_rate": 4.88112220637185e-05,
|
| 19 |
+
"loss": 1.9882,
|
| 20 |
+
"step": 100
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.21,
|
| 24 |
+
"learning_rate": 4.821683309557775e-05,
|
| 25 |
+
"loss": 1.9831,
|
| 26 |
+
"step": 150
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.29,
|
| 30 |
+
"learning_rate": 4.7622444127437e-05,
|
| 31 |
+
"loss": 1.9557,
|
| 32 |
+
"step": 200
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.36,
|
| 36 |
+
"learning_rate": 4.702805515929625e-05,
|
| 37 |
+
"loss": 1.94,
|
| 38 |
+
"step": 250
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.43,
|
| 42 |
+
"learning_rate": 4.64336661911555e-05,
|
| 43 |
+
"loss": 1.9083,
|
| 44 |
+
"step": 300
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.5,
|
| 48 |
+
"learning_rate": 4.583927722301474e-05,
|
| 49 |
+
"loss": 1.8826,
|
| 50 |
+
"step": 350
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.57,
|
| 54 |
+
"learning_rate": 4.524488825487399e-05,
|
| 55 |
+
"loss": 1.8844,
|
| 56 |
+
"step": 400
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.64,
|
| 60 |
+
"learning_rate": 4.4650499286733236e-05,
|
| 61 |
+
"loss": 1.8795,
|
| 62 |
+
"step": 450
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.71,
|
| 66 |
+
"learning_rate": 4.405611031859249e-05,
|
| 67 |
+
"loss": 1.824,
|
| 68 |
+
"step": 500
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.78,
|
| 72 |
+
"learning_rate": 4.346172135045174e-05,
|
| 73 |
+
"loss": 1.8521,
|
| 74 |
+
"step": 550
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.86,
|
| 78 |
+
"learning_rate": 4.286733238231099e-05,
|
| 79 |
+
"loss": 1.8458,
|
| 80 |
+
"step": 600
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.93,
|
| 84 |
+
"learning_rate": 4.2272943414170235e-05,
|
| 85 |
+
"loss": 1.8471,
|
| 86 |
+
"step": 650
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.0,
|
| 90 |
+
"learning_rate": 4.167855444602948e-05,
|
| 91 |
+
"loss": 1.8285,
|
| 92 |
+
"step": 700
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.07,
|
| 96 |
+
"learning_rate": 4.108416547788873e-05,
|
| 97 |
+
"loss": 1.805,
|
| 98 |
+
"step": 750
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.14,
|
| 102 |
+
"learning_rate": 4.048977650974798e-05,
|
| 103 |
+
"loss": 1.8047,
|
| 104 |
+
"step": 800
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.21,
|
| 108 |
+
"learning_rate": 3.9895387541607234e-05,
|
| 109 |
+
"loss": 1.7814,
|
| 110 |
+
"step": 850
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.28,
|
| 114 |
+
"learning_rate": 3.930099857346648e-05,
|
| 115 |
+
"loss": 1.7758,
|
| 116 |
+
"step": 900
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.36,
|
| 120 |
+
"learning_rate": 3.870660960532573e-05,
|
| 121 |
+
"loss": 1.7936,
|
| 122 |
+
"step": 950
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.43,
|
| 126 |
+
"learning_rate": 3.811222063718498e-05,
|
| 127 |
+
"loss": 1.7921,
|
| 128 |
+
"step": 1000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.5,
|
| 132 |
+
"learning_rate": 3.751783166904422e-05,
|
| 133 |
+
"loss": 1.7829,
|
| 134 |
+
"step": 1050
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.57,
|
| 138 |
+
"learning_rate": 3.692344270090347e-05,
|
| 139 |
+
"loss": 1.7711,
|
| 140 |
+
"step": 1100
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.64,
|
| 144 |
+
"learning_rate": 3.6329053732762716e-05,
|
| 145 |
+
"loss": 1.756,
|
| 146 |
+
"step": 1150
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.71,
|
| 150 |
+
"learning_rate": 3.573466476462197e-05,
|
| 151 |
+
"loss": 1.7642,
|
| 152 |
+
"step": 1200
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.78,
|
| 156 |
+
"learning_rate": 3.514027579648122e-05,
|
| 157 |
+
"loss": 1.7685,
|
| 158 |
+
"step": 1250
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.85,
|
| 162 |
+
"learning_rate": 3.454588682834047e-05,
|
| 163 |
+
"loss": 1.7459,
|
| 164 |
+
"step": 1300
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.93,
|
| 168 |
+
"learning_rate": 3.3951497860199716e-05,
|
| 169 |
+
"loss": 1.7326,
|
| 170 |
+
"step": 1350
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.0,
|
| 174 |
+
"learning_rate": 3.3357108892058964e-05,
|
| 175 |
+
"loss": 1.7509,
|
| 176 |
+
"step": 1400
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.07,
|
| 180 |
+
"learning_rate": 3.276271992391821e-05,
|
| 181 |
+
"loss": 1.7287,
|
| 182 |
+
"step": 1450
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.14,
|
| 186 |
+
"learning_rate": 3.216833095577747e-05,
|
| 187 |
+
"loss": 1.7122,
|
| 188 |
+
"step": 1500
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.21,
|
| 192 |
+
"learning_rate": 3.1573941987636715e-05,
|
| 193 |
+
"loss": 1.7116,
|
| 194 |
+
"step": 1550
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.28,
|
| 198 |
+
"learning_rate": 3.097955301949596e-05,
|
| 199 |
+
"loss": 1.7294,
|
| 200 |
+
"step": 1600
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.35,
|
| 204 |
+
"learning_rate": 3.0385164051355208e-05,
|
| 205 |
+
"loss": 1.7168,
|
| 206 |
+
"step": 1650
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.43,
|
| 210 |
+
"learning_rate": 2.9790775083214456e-05,
|
| 211 |
+
"loss": 1.7184,
|
| 212 |
+
"step": 1700
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.5,
|
| 216 |
+
"learning_rate": 2.9196386115073704e-05,
|
| 217 |
+
"loss": 1.712,
|
| 218 |
+
"step": 1750
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.57,
|
| 222 |
+
"learning_rate": 2.8601997146932952e-05,
|
| 223 |
+
"loss": 1.7183,
|
| 224 |
+
"step": 1800
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.64,
|
| 228 |
+
"learning_rate": 2.8007608178792204e-05,
|
| 229 |
+
"loss": 1.7,
|
| 230 |
+
"step": 1850
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.71,
|
| 234 |
+
"learning_rate": 2.7413219210651452e-05,
|
| 235 |
+
"loss": 1.7197,
|
| 236 |
+
"step": 1900
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.78,
|
| 240 |
+
"learning_rate": 2.68188302425107e-05,
|
| 241 |
+
"loss": 1.6767,
|
| 242 |
+
"step": 1950
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.85,
|
| 246 |
+
"learning_rate": 2.6224441274369948e-05,
|
| 247 |
+
"loss": 1.6995,
|
| 248 |
+
"step": 2000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.92,
|
| 252 |
+
"learning_rate": 2.5630052306229196e-05,
|
| 253 |
+
"loss": 1.708,
|
| 254 |
+
"step": 2050
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.0,
|
| 258 |
+
"learning_rate": 2.5035663338088444e-05,
|
| 259 |
+
"loss": 1.6798,
|
| 260 |
+
"step": 2100
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.07,
|
| 264 |
+
"learning_rate": 2.4441274369947696e-05,
|
| 265 |
+
"loss": 1.6932,
|
| 266 |
+
"step": 2150
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 3.14,
|
| 270 |
+
"learning_rate": 2.3846885401806944e-05,
|
| 271 |
+
"loss": 1.6818,
|
| 272 |
+
"step": 2200
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.21,
|
| 276 |
+
"learning_rate": 2.3252496433666192e-05,
|
| 277 |
+
"loss": 1.6774,
|
| 278 |
+
"step": 2250
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 3.28,
|
| 282 |
+
"learning_rate": 2.265810746552544e-05,
|
| 283 |
+
"loss": 1.6839,
|
| 284 |
+
"step": 2300
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.35,
|
| 288 |
+
"learning_rate": 2.206371849738469e-05,
|
| 289 |
+
"loss": 1.6666,
|
| 290 |
+
"step": 2350
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 3.42,
|
| 294 |
+
"learning_rate": 2.146932952924394e-05,
|
| 295 |
+
"loss": 1.6789,
|
| 296 |
+
"step": 2400
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.5,
|
| 300 |
+
"learning_rate": 2.0874940561103188e-05,
|
| 301 |
+
"loss": 1.6442,
|
| 302 |
+
"step": 2450
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.57,
|
| 306 |
+
"learning_rate": 2.0280551592962436e-05,
|
| 307 |
+
"loss": 1.665,
|
| 308 |
+
"step": 2500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 3.64,
|
| 312 |
+
"learning_rate": 1.9686162624821684e-05,
|
| 313 |
+
"loss": 1.6517,
|
| 314 |
+
"step": 2550
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 3.71,
|
| 318 |
+
"learning_rate": 1.9091773656680932e-05,
|
| 319 |
+
"loss": 1.6802,
|
| 320 |
+
"step": 2600
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 3.78,
|
| 324 |
+
"learning_rate": 1.849738468854018e-05,
|
| 325 |
+
"loss": 1.6548,
|
| 326 |
+
"step": 2650
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 3.85,
|
| 330 |
+
"learning_rate": 1.790299572039943e-05,
|
| 331 |
+
"loss": 1.6595,
|
| 332 |
+
"step": 2700
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 3.92,
|
| 336 |
+
"learning_rate": 1.730860675225868e-05,
|
| 337 |
+
"loss": 1.6514,
|
| 338 |
+
"step": 2750
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.99,
|
| 342 |
+
"learning_rate": 1.6714217784117928e-05,
|
| 343 |
+
"loss": 1.6224,
|
| 344 |
+
"step": 2800
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 4.07,
|
| 348 |
+
"learning_rate": 1.6119828815977176e-05,
|
| 349 |
+
"loss": 1.6501,
|
| 350 |
+
"step": 2850
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 4.14,
|
| 354 |
+
"learning_rate": 1.5525439847836425e-05,
|
| 355 |
+
"loss": 1.6449,
|
| 356 |
+
"step": 2900
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 4.21,
|
| 360 |
+
"learning_rate": 1.4931050879695674e-05,
|
| 361 |
+
"loss": 1.6359,
|
| 362 |
+
"step": 2950
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 4.28,
|
| 366 |
+
"learning_rate": 1.433666191155492e-05,
|
| 367 |
+
"loss": 1.6545,
|
| 368 |
+
"step": 3000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 4.35,
|
| 372 |
+
"learning_rate": 1.3742272943414172e-05,
|
| 373 |
+
"loss": 1.6488,
|
| 374 |
+
"step": 3050
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.42,
|
| 378 |
+
"learning_rate": 1.314788397527342e-05,
|
| 379 |
+
"loss": 1.6471,
|
| 380 |
+
"step": 3100
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 4.49,
|
| 384 |
+
"learning_rate": 1.2553495007132669e-05,
|
| 385 |
+
"loss": 1.6382,
|
| 386 |
+
"step": 3150
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 4.56,
|
| 390 |
+
"learning_rate": 1.1959106038991917e-05,
|
| 391 |
+
"loss": 1.6295,
|
| 392 |
+
"step": 3200
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 4.64,
|
| 396 |
+
"learning_rate": 1.1364717070851165e-05,
|
| 397 |
+
"loss": 1.639,
|
| 398 |
+
"step": 3250
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 4.71,
|
| 402 |
+
"learning_rate": 1.0770328102710415e-05,
|
| 403 |
+
"loss": 1.658,
|
| 404 |
+
"step": 3300
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 4.78,
|
| 408 |
+
"learning_rate": 1.0175939134569663e-05,
|
| 409 |
+
"loss": 1.6175,
|
| 410 |
+
"step": 3350
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 4.85,
|
| 414 |
+
"learning_rate": 9.581550166428911e-06,
|
| 415 |
+
"loss": 1.6206,
|
| 416 |
+
"step": 3400
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 4.92,
|
| 420 |
+
"learning_rate": 8.98716119828816e-06,
|
| 421 |
+
"loss": 1.6117,
|
| 422 |
+
"step": 3450
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 4.99,
|
| 426 |
+
"learning_rate": 8.392772230147409e-06,
|
| 427 |
+
"loss": 1.6444,
|
| 428 |
+
"step": 3500
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 5.06,
|
| 432 |
+
"learning_rate": 7.798383262006657e-06,
|
| 433 |
+
"loss": 1.6149,
|
| 434 |
+
"step": 3550
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 5.14,
|
| 438 |
+
"learning_rate": 7.203994293865907e-06,
|
| 439 |
+
"loss": 1.6161,
|
| 440 |
+
"step": 3600
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 5.21,
|
| 444 |
+
"learning_rate": 6.609605325725154e-06,
|
| 445 |
+
"loss": 1.6028,
|
| 446 |
+
"step": 3650
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 5.28,
|
| 450 |
+
"learning_rate": 6.015216357584404e-06,
|
| 451 |
+
"loss": 1.5863,
|
| 452 |
+
"step": 3700
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 5.35,
|
| 456 |
+
"learning_rate": 5.420827389443652e-06,
|
| 457 |
+
"loss": 1.6134,
|
| 458 |
+
"step": 3750
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 5.42,
|
| 462 |
+
"learning_rate": 4.826438421302901e-06,
|
| 463 |
+
"loss": 1.6042,
|
| 464 |
+
"step": 3800
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 5.49,
|
| 468 |
+
"learning_rate": 4.232049453162149e-06,
|
| 469 |
+
"loss": 1.6399,
|
| 470 |
+
"step": 3850
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 5.56,
|
| 474 |
+
"learning_rate": 3.6376604850213982e-06,
|
| 475 |
+
"loss": 1.6152,
|
| 476 |
+
"step": 3900
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 5.63,
|
| 480 |
+
"learning_rate": 3.0432715168806468e-06,
|
| 481 |
+
"loss": 1.6052,
|
| 482 |
+
"step": 3950
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 5.71,
|
| 486 |
+
"learning_rate": 2.4488825487398953e-06,
|
| 487 |
+
"loss": 1.6143,
|
| 488 |
+
"step": 4000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 5.78,
|
| 492 |
+
"learning_rate": 1.8544935805991443e-06,
|
| 493 |
+
"loss": 1.5915,
|
| 494 |
+
"step": 4050
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 5.85,
|
| 498 |
+
"learning_rate": 1.2601046124583929e-06,
|
| 499 |
+
"loss": 1.6259,
|
| 500 |
+
"step": 4100
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 5.92,
|
| 504 |
+
"learning_rate": 6.657156443176415e-07,
|
| 505 |
+
"loss": 1.5607,
|
| 506 |
+
"step": 4150
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 5.99,
|
| 510 |
+
"learning_rate": 7.132667617689017e-08,
|
| 511 |
+
"loss": 1.6125,
|
| 512 |
+
"step": 4200
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 6.0,
|
| 516 |
+
"step": 4206,
|
| 517 |
+
"total_flos": 4430921691561984.0,
|
| 518 |
+
"train_loss": 1.717211879325718,
|
| 519 |
+
"train_runtime": 1445.1612,
|
| 520 |
+
"train_samples_per_second": 93.037,
|
| 521 |
+
"train_steps_per_second": 2.91
|
| 522 |
+
}
|
| 523 |
+
],
|
| 524 |
+
"max_steps": 4206,
|
| 525 |
+
"num_train_epochs": 6,
|
| 526 |
+
"total_flos": 4430921691561984.0,
|
| 527 |
+
"trial_name": null,
|
| 528 |
+
"trial_params": null
|
| 529 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65c114965637df0290580a1a51bb839c9df7a1e89b7526583137c02f42812e23
|
| 3 |
+
size 2799
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|